CtrlK
BlogDocsLog inGet started
Tessl Logo

survey-sdk-audit

Audit PostHog survey SDK features and version requirements, and implement survey changes across the backend, UI, and SDK repositories.

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/survey-sdk-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, highly actionable audit playbook rich with real domain specifics, with clear sequencing and useful validation checkpoints. Its main weaknesses are some repetition and meta-padding that hurt conciseness, and a signaled reference to a references/ file that does not exist in the bundle.

Suggestions

Create the referenced references/contributing-surveys.md (or remove the dangling link) so the signaled progressive-disclosure path resolves to a real file.

De-duplicate Common Pitfalls items #8 and #9 against Step 5's rendering/Android guidance to tighten conciseness.

Extract the issue template and output-format blocks into a separate reference file to reduce inline bulk and improve navigation.

DimensionReasoningScore

Conciseness

Most content is genuine PostHog-specific domain knowledge Claude lacks (exact SDK file paths, utility functions, pitfall examples) that earns its place, but the Common Pitfalls section repeats Step 5 material (Android delegate-only, rendering-code checks) and the Post-Audit section adds meta-process padding that could be tightened, fitting the 'mostly efficient but some unnecessary explanation' anchor.

3 / 5

Actionability

The body provides concrete, executable commands (grep, git log -S, git tag --contains, gh issue list/create/edit) with exact file paths and a copy-paste output format, but template placeholders (KEYWORD, X.Y.Z, COMMIT_HASH) require substitution, fitting the 'mostly executable guidance with minor gaps' anchor rather than fully copy-paste ready.

4 / 5

Workflow Clarity

The audit process is clearly sequenced (Setup Check, Steps 1-5, issue creation, backfill, completion checklist) with validation checkpoints (path verification, search-before-create, temp-file review before pushing), but the core audit Steps 2-4 are sequential without explicit validate-and-retry feedback loops, fitting the 'clear sequence with most checkpoints; minor validation gaps' anchor.

4 / 5

Progressive Disclosure

Clear section headers give the body reasonable structure, and one reference is signaled ('read [Contributing survey changes](references/contributing-surveys.md)'), but no references/ bundle directory exists so that link is dangling, and sizable content that could live in separate files (issue template, output format) is inlined, fitting the 'some structure but could be better organized; references present but not backed by real files' anchor.

3 / 5

Total

14

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is domain-specific and states clear actions, but it omits any explicit 'Use when' trigger guidance, which caps completeness, and broadens scope with an implementation clause that slightly raises overlap risk. It is a solid, mid-range description that would benefit from explicit trigger phrasing.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., 'Use when auditing survey feature support across PostHog SDKs or updating surveyVersionRequirements.ts').

Resolve the scope mismatch between the description's 'implement survey changes across the backend, UI, and SDK repositories' and the body, which is focused on auditing — either widen the body or narrow the description.

Include natural synonyms users would say ('survey feature parity', 'SDK version requirements', 'surveyVersionRequirements') to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description names a concrete domain ('PostHog survey SDK features and version requirements') and two action categories ('Audit ... and implement survey changes across the backend, UI, and SDK repositories'), matching the anchor that names the domain plus 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

The 'what' is clearly stated (audit SDK features/version requirements, implement survey changes) but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ('PostHog', 'survey SDK', 'version requirements', 'survey changes') but common natural variations users would say (e.g., 'survey feature support', 'SDK parity', 'feature audit') are missing, fitting the 'some relevant keywords but missing synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The PostHog-specific survey SDK niche is mostly distinct with minimal conflict risk, though the second clause ('implement survey changes across the backend, UI, and SDK repositories') broadens scope enough to risk minor overlap with general PostHog survey skills, fitting the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

13

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
PostHog/posthog
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.